Steward Garcia

@leejet It's my impression or it seems that the CUDA backend is experiencing synchronization issues even from the CLIP model; it tends to happen sometimes. ```bash build\bin\Release\sd -m models/kotosmix_v10-f16.gguf -p...

@Cyberhan123 Could you send me the CLI commands to perform this test? Your link is not allowing me to access Colab.

@leejet to fix race condition of softmax in cuda comment the line 6499, this may solve the errors with artifacts when using VAE tiling: ```c++ while (nth < ncols_x &&...

I think it would be better to support Vulkan backend for acceleration on Android devices, as ggml currently lacks good support for OpenCL (it is even considered obsolete). Unfortunately, I...

@Jonathhhan I don't understand this case you're raising. Are you referring to reloading the model? Or deleting an already created context and creating a new one? Or that when you...

@leejet To fix this need this modification in ggml.c line 12401: ```bash if(dst->op_params[0] == 1) { // masked GGML_ASSERT(P >= 0); } ```

@leejet The GGUF file support is broken, you need to set GGML_MAX_NAME to 128 to prevent it from crashing when loading the model.

I am thinking about implementing a REST API for image generation, but time has not allowed me. Additionally, this project changes a lot, and it's not worth it for me...

Hello everyone, I have a llama.cpp with cpp-httplib [here](https://github.com/FSSRepo/llama.cpp). It doesn't require external dependencies. ## Limitations: * Just tested in Windows and Linux * Only CMake build. * Only one...

@x4080 you can detail the error in Issues tab on my fork, please